Person Re-identification Based on Relaxed Nonnegative Matrix Factorization with Regularizations

We address the person reidentification problem by efficient data representation method. Based on the Relaxed Nonnegative matrix factorization (rNMF) which has no sign constraints on the data matrix and the basis matrix, we consider two regularizations to improve the Relaxed NMF, which are the local manifold assumption and a rank constraint. The local manifold assumption helps preserve the geometry structure of the data and the rank constraint helps improve the discrimination and the sparsity of the data representations. When only the manifold regularization is considered, we propose the Relaxed Graph regularized NMF (rGNMF). When both two regularizations are considered, we propose the Relaxed NMF with regularizations (rRNMF). To demonstrate our proposed methods, we run experiments on two different publicly available datasets, showing state-of-the-art or even better results, however, on much lower computational efforts.